Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 349 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 3.8351. Min Range: -3.8351

Max Act: 3.8351. Min Act: -0.1700

Data Index: 7040138 (Open Web Text)

Max Activating Token Index: 34

Text #1

Max Range: 3.8351. Min Range: -3.8351

Max Act: 3.6899. Min Act: -0.1700

Data Index: 1490996 (Open Web Text)

Max Activating Token Index: 46

Text #2

Max Range: 3.8351. Min Range: -3.8351

Max Act: 3.6562. Min Act: -0.1700

Data Index: 2410814 (Open Web Text)

Max Activating Token Index: 560

Text #3

Max Range: 3.8351. Min Range: -3.8351

Max Act: 3.6353. Min Act: -0.1700

Data Index: 8037458 (Open Web Text)

Max Activating Token Index: 745

Text #4

Max Range: 3.8351. Min Range: -3.8351

Max Act: 3.6280. Min Act: -0.1700

Data Index: 5523424 (Open Web Text)

Max Activating Token Index: 715

Text #5

Max Range: 3.8351. Min Range: -3.8351

Max Act: 3.6405. Min Act: -0.1700

Data Index: 4960014 (Open Web Text)

Max Activating Token Index: 582

Text #6

Max Range: 3.8351. Min Range: -3.8351

Max Act: 3.5843. Min Act: -0.1700

Data Index: 1409048 (Open Web Text)

Max Activating Token Index: 410

Text #7

Max Range: 3.8351. Min Range: -3.8351

Max Act: 3.5617. Min Act: -0.1700

Data Index: 2855772 (Open Web Text)

Max Activating Token Index: 469

Text #8

Max Range: 3.8351. Min Range: -3.8351

Max Act: 3.6168. Min Act: -0.1700

Data Index: 7036464 (Open Web Text)

Max Activating Token Index: 855

Text #9

Max Range: 3.8351. Min Range: -3.8351

Max Act: 3.5542. Min Act: -0.1700

Data Index: 5261461 (Open Web Text)

Max Activating Token Index: 233

Text #10

Max Range: 3.8351. Min Range: -3.8351

Max Act: 3.5793. Min Act: -0.1700

Data Index: 6830912 (Open Web Text)

Max Activating Token Index: 411

Text #11

Max Range: 3.8351. Min Range: -3.8351

Max Act: 3.5614. Min Act: -0.1700

Data Index: 6011435 (Open Web Text)

Max Activating Token Index: 686

Text #12

Max Range: 3.8351. Min Range: -3.8351

Max Act: 3.5481. Min Act: -0.1700

Data Index: 7942912 (Open Web Text)

Max Activating Token Index: 430

Text #13

Max Range: 3.8351. Min Range: -3.8351

Max Act: 3.5471. Min Act: -0.1700

Data Index: 3622781 (Open Web Text)

Max Activating Token Index: 921

Text #14

Max Range: 3.8351. Min Range: -3.8351

Max Act: 3.5179. Min Act: -0.1700

Data Index: 6361182 (Open Web Text)

Max Activating Token Index: 57

Text #15

Max Range: 3.8351. Min Range: -3.8351

Max Act: 3.5192. Min Act: -0.1700

Data Index: 5642483 (Open Web Text)

Max Activating Token Index: 430

Text #16

Max Range: 3.8351. Min Range: -3.8351

Max Act: 3.4989. Min Act: -0.1700

Data Index: 5757570 (Open Web Text)

Max Activating Token Index: 512

Text #17

Max Range: 3.8351. Min Range: -3.8351

Max Act: 3.4712. Min Act: -0.1700

Data Index: 482012 (Open Web Text)

Max Activating Token Index: 755

Text #18

Max Range: 3.8351. Min Range: -3.8351

Max Act: 3.4678. Min Act: -0.1700

Data Index: 393852 (Open Web Text)

Max Activating Token Index: 333

Text #19

Max Range: 3.8351. Min Range: -3.8351

Max Act: 3.4844. Min Act: -0.1700

Data Index: 6238073 (Open Web Text)

Max Activating Token Index: 548